{"id":"https://openalex.org/W1570774895","doi":"https://doi.org/10.21437/eurospeech.1991-206","title":"Improving short-time speech frame recognition results by using context","display_name":"Improving short-time speech frame recognition results by using context","publication_year":1991,"publication_date":"1991-09-24","ids":{"openalex":"https://openalex.org/W1570774895","doi":"https://doi.org/10.21437/eurospeech.1991-206","mag":"1570774895"},"language":"en","primary_location":{"id":"doi:10.21437/eurospeech.1991-206","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1991-206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2nd European Conference on Speech Communication and Technology (Eurospeech 1991)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112199217","display_name":"Kari Torkkola","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kari Torkkola","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103194538","display_name":"Mikko Kokkonen","orcid":"https://orcid.org/0000-0001-8287-485X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikko Kokkonen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043424064","display_name":"Mikko Kurimo","orcid":"https://orcid.org/0000-0001-5278-7974"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikko Kurimo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026617295","display_name":"Pekka Utela","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pekka Utela","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"793","last_page":"796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9038000106811523,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9038000106811523,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7738383412361145},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.695459246635437},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6674504280090332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.655608057975769},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37185877561569214},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33630573749542236},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11938929557800293},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.060038089752197266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738383412361145},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.695459246635437},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6674504280090332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.655608057975769},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37185877561569214},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33630573749542236},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11938929557800293},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.060038089752197266},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/eurospeech.1991-206","is_oa":false,"landing_page_url":"https://doi.org/10.21437/eurospeech.1991-206","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2nd European Conference on Speech Communication and Technology (Eurospeech 1991)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.30.8086","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.30.8086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.idiap.ch/pub/papers/speech/torkkola.eurospeech91.ps.Z","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W2389546251","https://openalex.org/W2369556382","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"paper":[1,115],"focuses":[2],"on":[3,55,62,138],"comparing":[4],"three":[5],"approaches":[6],"to":[7,39,89,120],"improve":[8],"the":[9,23,40,60,80,106],"accuracy":[10,41],"of":[11,25,42,96,104,123],"classifying":[12,139],"short-time":[13],"speech":[14,44,135],"frames":[15],"into":[16,21,45,83],"phoneme":[17,46],"classes":[18],"by":[19,78,92,100],"taking":[20,79],"account":[22],"classifications":[24],"nearby":[26],"frames,":[27],"also":[28],"individually":[29],"classified.":[30],"We":[31],"investigate":[32],"whether":[33],"this":[34,114],"improvement":[35],"has":[36],"an":[37],"effect":[38],"transcribing":[43],"sequences":[47],"using":[48],"two":[49],"different":[50],"decoding":[51],"schemes,":[52],"one":[53],"based":[54,137],"simple":[56],"durational":[57],"rules,":[58],"and":[59],"other":[61],"hidden":[63],"Markov":[64],"models":[65],"(HMMs).":[66],"The":[67,143],"experiments":[68],"indicate":[69],"that":[70],"recognition":[71],"accuracies":[72],"can":[73],"indeed":[74],"be":[75,90],"improved":[76],"significantly":[77],"local":[81,107,124],"context":[82,98,125],"account.":[84],"1":[85],"INTRODUCTION":[86],""More":[87],"is":[88,132],"gained":[91],"discovering":[93,101],"suboptimal":[94],"ways":[95,103],"handling":[97,105],"than":[99],"optimal":[102],"structure",":[108],"Haralick":[109],"stated":[110],"in":[111,126],"[2].":[112],"In":[113],"we":[116],"explore":[117],"some":[118],"options":[119],"take":[121],"advantage":[122],"improving":[127],"classification":[128],"accuracy.":[129],"Our":[130],"framework":[131],"a":[133],"phonemic":[134],"recognizer":[136],"shorttime":[140],"feature":[141],"vectors.":[142],"viewpoint":[144],"taken":[145],"i...":[146]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}